Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler changes from Ingo Molnar:
 "The main changes are:

   - irqtime accounting cleanups and enhancements. (Frederic Weisbecker)

   - schedstat debugging enhancements, make it more broadly runtime
     available. (Josh Poimboeuf)

   - More work on asymmetric topology/capacity scheduling. (Morten
     Rasmussen)

   - sched/wait fixes and cleanups. (Oleg Nesterov)

   - PELT (per entity load tracking) improvements. (Peter Zijlstra)

   - Rewrite and enhance select_idle_siblings(). (Peter Zijlstra)

   - sched/numa enhancements/fixes (Rik van Riel)

   - sched/cputime scalability improvements (Stanislaw Gruszka)

   - Load calculation arithmetics fixes. (Dietmar Eggemann)

   - sched/deadline enhancements (Tommaso Cucinotta)

   - Fix utilization accounting when switching to the SCHED_NORMAL
     policy. (Vincent Guittot)

   - ... plus misc cleanups and enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/irqtime: Consolidate irqtime flushing code
  sched/irqtime: Consolidate accounting synchronization with u64_stats API
  u64_stats: Introduce IRQs disabled helpers
  sched/irqtime: Remove needless IRQs disablement on kcpustat update
  sched/irqtime: No need for preempt-safe accessors
  sched/fair: Fix min_vruntime tracking
  sched/debug: Add SCHED_WARN_ON()
  sched/core: Fix set_user_nice()
  sched/fair: Introduce set_curr_task() helper
  sched/core, ia64: Rename set_curr_task()
  sched/core: Fix incorrect utilization accounting when switching to fair class
  sched/core: Optimize SCHED_SMT
  sched/core: Rewrite and improve select_idle_siblings()
  sched/core: Replace sd_busy/nr_busy_cpus with sched_domain_shared
  sched/core: Introduce 'struct sched_domain_shared'
  sched/core: Restructure destroy_sched_domain()
  sched/core: Remove unused @cpu argument from destroy_sched_domain*()
  sched/wait: Introduce init_wait_entry()
  sched/wait: Avoid abort_exclusive_wait() in __wait_on_bit_lock()
  sched/wait: Avoid abort_exclusive_wait() in ___wait_event()
  ...

2 files changed, 35 insertions, 21 deletions

diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index eb9220cde76c..d47616c8b885 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -986,7 +986,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
 	int cpu = smp_processor_id();
 
 	previous_current = curr_task(cpu);
-	set_curr_task(cpu, current);
+	ia64_set_curr_task(cpu, current);
 	if ((p = strchr(current->comm, ' ')))
 		*p = '\0';
 
@@ -1360,14 +1360,14 @@ ia64_mca_handler(struct pt_regs *regs, struct switch_stack *sw,
 				cpumask_clear_cpu(i, &mca_cpu);	/* wake next cpu */
 				while (monarch_cpu != -1)
 					cpu_relax();	/* spin until last cpu leaves */
-				set_curr_task(cpu, previous_current);
+				ia64_set_curr_task(cpu, previous_current);
 				ia64_mc_info.imi_rendez_checkin[cpu]
 						= IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
 				return;
 			}
 		}
 	}
-	set_curr_task(cpu, previous_current);
+	ia64_set_curr_task(cpu, previous_current);
 	ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
 	monarch_cpu = -1;	/* This frees the slaves and previous monarchs */
 }
@@ -1729,7 +1729,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
 		NOTIFY_INIT(DIE_INIT_SLAVE_LEAVE, regs, (long)&nd, 1);
 
 		mprintk("Slave on cpu %d returning to normal service.\n", cpu);
-		set_curr_task(cpu, previous_current);
+		ia64_set_curr_task(cpu, previous_current);
 		ia64_mc_info.imi_rendez_checkin[cpu] = IA64_MCA_RENDEZ_CHECKIN_NOTDONE;
 		atomic_dec(&slaves);
 		return;
@@ -1756,7 +1756,7 @@ ia64_init_handler(struct pt_regs *regs, struct switch_stack *sw,
 
 	mprintk("\nINIT dump complete.  Monarch on cpu %d returning to normal service.\n", cpu);
 	atomic_dec(&monarchs);
-	set_curr_task(cpu, previous_current);
+	ia64_set_curr_task(cpu, previous_current);
 	monarch_cpu = -1;
 	return;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4296beb8fdd3..7137ec4eea9a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -471,7 +471,7 @@ static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 	return false;
 }
 
-static struct sched_domain_topology_level numa_inside_package_topology[] = {
+static struct sched_domain_topology_level x86_numa_in_package_topology[] = {
 #ifdef CONFIG_SCHED_SMT
 	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 #endif
@@ -480,22 +480,23 @@ static struct sched_domain_topology_level numa_inside_package_topology[] = {
 #endif
 	{ NULL, },
 };
+
+static struct sched_domain_topology_level x86_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
 /*
- * set_sched_topology() sets the topology internal to a CPU.  The
- * NUMA topologies are layered on top of it to build the full
- * system topology.
- *
- * If NUMA nodes are observed to occur within a CPU package, this
- * function should be called.  It forces the sched domain code to
- * only use the SMT level for the CPU portion of the topology.
- * This essentially falls back to relying on NUMA information
- * from the SRAT table to describe the entire system topology
- * (except for hyperthreads).
+ * Set if a package/die has multiple NUMA nodes inside.
+ * AMD Magny-Cours and Intel Cluster-on-Die have this.
  */
-static void primarily_use_numa_for_topology(void)
-{
-	set_sched_topology(numa_inside_package_topology);
-}
+static bool x86_has_numa_in_package;
 
 void set_cpu_sibling_map(int cpu)
 {
@@ -558,7 +559,7 @@ void set_cpu_sibling_map(int cpu)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
 		if (match_die(c, o) && !topology_same_node(c, o))
-			primarily_use_numa_for_topology();
+			x86_has_numa_in_package = true;
 	}
 
 	threads = cpumask_weight(topology_sibling_cpumask(cpu));
@@ -1304,6 +1305,16 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
 		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
 	}
+
+	/*
+	 * Set 'default' x86 topology, this matches default_topology() in that
+	 * it has NUMA nodes as a topology level. See also
+	 * native_smp_cpus_done().
+	 *
+	 * Must be done before set_cpus_sibling_map() is ran.
+	 */
+	set_sched_topology(x86_topology);
+
 	set_cpu_sibling_map(0);
 
 	switch (smp_sanity_check(max_cpus)) {
@@ -1370,6 +1381,9 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 {
 	pr_debug("Boot done\n");
 
+	if (x86_has_numa_in_package)
+		set_sched_topology(x86_numa_in_package_topology);
+
 	nmi_selftest();
 	impress_friends();
 	setup_ioapic_dest();